N-Cloth: Predicting 3D Cloth Deformation with Mesh-Based Networks

Li, Yu Di; Tang, Min; Yang, Yun; Huang, Zi; Tong, Ruo Feng; Yang, Shuang Cai; Li, Yao; Manocha, Dinesh

N-Cloth: Predicting 3D Cloth Deformation with Mesh-Based Networks

Files

v41i2pp547-558.pdf (10.15 MB)

paper1100_1.pdf (2.18 MB)

Date

2022

Authors

Li, Yu Di
Tang, Min
Yang, Yun
Huang, Zi
Tong, Ruo Feng
Yang, Shuang Cai
Li, Yao
Manocha, Dinesh

Publisher

The Eurographics Association and John Wiley & Sons Ltd.

Abstract

We present a novel mesh-based learning approach (N-Cloth) for plausible 3D cloth deformation prediction. Our approach is general and can handle cloth or obstacles represented by triangle meshes with arbitrary topologies.We use graph convolution to transform the cloth and object meshes into a latent space to reduce the non-linearity in the mesh space. Our network can predict the target 3D cloth mesh deformation based on the initial state of the cloth mesh template and the target obstacle mesh. Our approach can handle complex cloth meshes with up to 100K triangles and scenes with various objects corresponding to SMPL humans, non-SMPL humans or rigid bodies. In practice, our approach can be used to generate plausible cloth simulation at 30??45 fps on an NVIDIA GeForce RTX 3090 GPU. We highlight its benefits over prior learning-based methods and physicallybased cloth simulators.

CCS Concepts: Computing methodologies --> Machine learning; Physical simulation

        @article{10.1111:cgf.14493
,
journal = {Computer Graphics Forum},
title = {{N-Cloth: Predicting 3D Cloth Deformation with Mesh-Based Networks
}},
author = {Li, Yu Di and 
Tang, Min and 
Yang, Yun and 
Huang, Zi and 
Tong, Ruo Feng and 
Yang, Shuang Cai and 
Li, Yao and 
Manocha, Dinesh
},
year = {2022
},
publisher = {The Eurographics Association and John Wiley & Sons Ltd.
},
ISSN = {1467-8659
},
DOI = {10.1111/cgf.14493
}
}